Forgot your password?
typodupeerror
Linux Business IBM

IBM Reveals New Virtual Linux Environment 96

Posted by ScuttleMonkey
from the pave-the-way dept.
jenwren1010 writes to mention that IBM has just announced the new open beta version of their virtual Linux environment that allows users to run x86 Linux programs on POWER processor-based IBM System p servers. "Designed to reduce power, cooling and space by consolidating x86 Linux workloads on System p servers, it will eventually be released as the [rolls-off-the-tongue] 'IBM System p Application Virtual Environment (System p AVE).' With a 31.5% global revenue share during 2006, IBM hopes to build on System p UNIX success and extend firmly into the Linux marketplace. Considering there are almost 2,800 applications that already run natively on Linux on System p servers, the chances are good that it will succeed."
This discussion has been archived. No new comments can be posted.

IBM Reveals New Virtual Linux Environment

Comments Filter:
  • What's the point? (Score:4, Interesting)

    by Ed Avis (5917) <ed@membled.com> on Monday April 23, 2007 @05:32PM (#18845873) Homepage
    I don't get it, aren't almost all Linux programs able to build for pretty much any architecture? The only use for emulation would be binary-only proprietary software that's built for x86 only. And even there it should be pretty trivial for the vendor to port it to POWER.
    • by timeOday (582209)
      My question is, why use POWER processors at all? Why not just run a bunch of VMs on an x86 blade server?
      • Re:What's the point? (Score:4, Interesting)

        by Kadin2048 (468275) <slashdot.kadin@xoxFREEBSDy.net minus bsd> on Monday April 23, 2007 @06:38PM (#18846793) Homepage Journal
        I think Power (according to IBM, anyway) offers a lot better performance/watt and scales better up to supercomputer-ish sizes.

        And I think you can even integrate x86 blades into some of IBM's high-end systems for running Linux x86 binaries; the idea is with this new virtual environment, you wouldn't need to purchase the additional hardware.

        I see this whole thing as basically a bullet point that they can use when selling POWER to a prospective client -- they can put it out there as one architecture that will run most anything. (Well, except Windows stuff.)
        • I think Power (according to IBM, anyway) offers a lot better performance/watt and scales better up to supercomputer-ish sizes.

          You're partially correct. PowerPC procs scale massively but can't offer better performance/watt. This is one of the reasons that Apple dropped PowerPC in the Mac.

        • Nobody likes to talk about how much a Pseries solution COSTS.

          I can buy a lot of commodity hardware and power it for $100,000. Let's just say a decent Pseries will be an order of magnitude more expensive for the initial purchase, never mind the annual support agreements.
          • I can buy a lot of commodity hardware and power it for $100,000. Let's just say a decent Pseries will be an order of magnitude more expensive for the initial purchase, never mind the annual support

            True. In my (admittedly limited) experience though, IBM hardware generally gets aimed at organizations whose IT budgets are already fairly big (I won't say "bloated"), and are paying through the nose for support already.

            If you're looking at commodity servers and supporting them yourself, you're probably not going
            • "I think they're going for PHB appeal here. The idea is that you have one machine, one support contract, to one company, and that's the end of that. (In theory.)"

              Yes, I agree. One place to point the finger, one vendor to blame is what the PHB sees.

              In practice (yes, I work for a PHB that's high on IBM kool aid), IBM itself is split into various divisions and they like to point the finger at each other.

              "Sounds like a hardware problem."
              "No, that's a software problem."

              I think IBM has some great talent working o
        • Actually, speaking of Windows, Wine could probably run in that environment...
      • Power5, Power5+, Power6, etc. are very powerful server processors, more powerful than x86. Here are some specs for Power6, due out in a couple months:

        From Wikipedia
        "The POWER6 will be using approximately 790 million transistors and 341 mm large fabricated on an 65 nm process. It is expected to run faster than 5 GHz when released in mid 2007[2] but the company has noted prototypes have reached 6 GHz.[3] POWER6 reached first silicon in the middle of 2005[4] and finished products will be available in mid 2
    • by Biggerveggies (517226) on Monday April 23, 2007 @05:40PM (#18846015)
      The point is that you can run a unified infrastructure with scalable LPARS for different clients on one box (think p595).

      ie - the marketing term: "Power on Demand".
      • Re: (Score:2, Interesting)

        by Tinkster (831703)
        That's one good and fair comment; the other thing is that you can have
        one of those big irons running an x86 Linux that will run your "commercial
        product of choice" which is certified against a specific version of Linux
        w/o having to buy x86 hardware and gain expertise in using VMWare as well...

        • Re:What's the point? (Score:4, Informative)

          by Chanc_Gorkon (94133) <gorkon @ g m ail.com> on Monday April 23, 2007 @07:12PM (#18847183)
          Some good points, however the term big iron should not be applied here. Big iron would be a mainframe. Pseries machines are very powerful, however, they are very different in technology then a mainframe. They are a hybridization of technology that IBM built with POWER and of Mainframe like techn0ologies.

          This is a great idea. With micro partitioning on the pSeries and automatic load balancing, us pSeries admins don't need to learn VMware to run a farm of x86 based servers. Also, while most things are running on POWER already, sometimes it's not convenient to find binaries that will run on it plus how many of us have a spare pSeries machine just for compiles?? Also, there's a metric tone of commercial apps that run on x86 Linux and not many of them that run on PPC based distros.
      • by glwtta (532858)
        infrastructure with scalable LPARS

        Is that like when I dress up in a leather kilt, run around bashing people with a foam bat, and talk about "mead" and "ale" a lot?
    • Re: (Score:2, Insightful)

      by Anonymous Coward
      Obiously you've never tried to port from Linux to AIX. Sure, "Hello, World!" ports over just fine, but beyond that you're going to have issues. The gcc tools on AIX are not good. You're forced to use the AIX linker. Shared objects, static linking...good luck figuring out the differences from what you're used to on Linux and what they mean to your program. Oh, you want to throw a C++ exception from a library? Good luck.

      Trust me, this software will help a lot of people get their big apps working on AIX.
      • by Ed Avis (5917)
        I didn't mean to compare Linux/x86 to AIX... I meant why not just port the apps to Linux/PowerPC or Linux/POWER and run them that way?

        I was under the impression (just assumed it from reading the press release) that this was a big POWER-based Linux box that had some proprietary x86 emulator added on to run binary-only x86 apps... if in fact it's an AIX machine with an x86 emulator, well that's a little bit more, shall we say, exotic.

        It seems that IBM is barking up the wrong tree - much better to just port De
        • by C_Kode (102755)
          Porting your app isn't always "easy". Just ask Oracle when they ported it to Linux on PowerPC.
        • Re:What's the point? (Score:4, Informative)

          by Kadin2048 (468275) <slashdot.kadin@xoxFREEBSDy.net minus bsd> on Monday April 23, 2007 @06:46PM (#18846875) Homepage Journal
          Yeah I originally thought it was a compatibility layer that would let you run x86/Linux apps on POWER/AIX, but I don't think it's quite that.

          From TFA:

          IBM expects ISVs that don't already have a native Linux on POWER product to be able to expand their addressable market to System p servers at minimal cost by allowing them to run their existing x86 Linux applications on these servers without having to recompile, release new media or documentation, or maintain a unique product offering for POWER technology.
          So basically it's a way of taking x86/Linux binaries and running them on POWER/Linux without a recompile. (And, one assumes, if you're an end-user, without going back to the software's manufacturer and paying through the nose for a new POWER version; you can move from x86 to POWER and still use all your same apps, without buying new versions.)
      • by red crab (1044734)
        Ya that's fine. But the question is that how far will IBM go in supporting Linux. IBM will always want AIX to be the OS of it's choice on its proprietary hardware. Many of powerful features of AIX like hardware diagnostic tools, mksysb image backups, hot swap LVM are not available on Power Linux and probably will never be. Like GNU Toolbox for Linux, x86 Virtual Linux also seems like another feeble attempt by IBM to support Linux.

        Overall, Sun seems more committed than IBM as far as Linux support is conce
    • Re: (Score:3, Informative)

      by Gooner (28391)
      Well one reason it's useful is that it's possible to partition POWER servers down to tenths of a CPU so it's easy to find space to run something like p-AVE. Another is that SLES is licensed by the box rather than by CPUs or LPARs so anything that helps get more apps to run is a good thing.

      I've got a 16 CPU P570 here at work and we run Linux on it exclusively due to the cost, as AIX means that you get soaked on costlier licenses. I've done my share of trying to get apps (primarily statistical programs) to wo
  • by Anonymous Coward on Monday April 23, 2007 @05:32PM (#18845881)
    I think it's pretty cocky of IBM to do this while the SCO case is still before the courts. It may be a case of the hand that steals not knowing what the hand that conceals is doing This time it might get a slap!

    I recommend SCOX. It's a BUY.

    T_A
    • by Kz (4332)
      not really similar; SCO (the original SCO, of course) had a software emulation layer to run Linux binaries on top of it's own x86 Unix. it was an ABI emulation, not a processor emulation.

      i think there's something similar for BSD, Solaris, AIX... all other Unix players want to run Linux apps.
  • by Anonymous Coward
    what?
  • Power Saving? (Score:3, Interesting)

    by hawg2k (628081) on Monday April 23, 2007 @05:33PM (#18845893) Homepage
    It's been my experience that IBM's power architecture isn't really known for being "green". Can anyone provide some expertise behind the statement that running Linux VM's on the P hardware will really save energy in heating and cooling over other concepts like a rack of 1-U rack servers, a VMWare/Xen type solution on x86 hardware, or some type of blade solution?
    • by cgh4be (182894)
      I can't speak as to whether or not it's cheaper on a per server basis, but they do some pretty cool power management things on the POWER5 processors and it is supposed to get even better on POWER6. The big thing is that they turn off the portions of the processor that are not being used at any given time.
    • Re:Power Saving? (Score:5, Interesting)

      by Chanc_Gorkon (94133) <gorkon @ g m ail.com> on Monday April 23, 2007 @07:18PM (#18847263)
      You can buy ONE rack and it has 64 processors in it. Each of those 64 processors can be sheared down to 1/10th of a CPU partition. That would be 640 servers in one rack. Granted, you'd never want to run that many LPARS on a system, but you could come close. You can also share all 64 of these processors and each of the LPARS can look like a SMP system by setting a VP of 2 or higher. Granted alot of this will need proper tuning, but you can do a lot with a pSeries and shove alot of hardware into one rack. Also, with Partition Load manager, it can very how much CPU each partition gets by the load it's getting. Say one of the LPARS gets nailed all of a sudden. If the partition is uncapped or not reached it's cap, it can automatically grab as much CPU as needed.

      The pSeries machine CAN do what they describe.
      • ROFL

        "Granted, all of this will need proper tuning."

      • Yeah, you can buy that one rack. It'll cost you a mil or so, but never mind that, you're worried about saving some kW.

        Those racks need one BIG ASS plug for power, as in some serious AMPs. The one I saw was 4 inches in diameter and had "pins" that looked like pencils. When powered on, the rack was blowing air at 35 MPH, never mind the noise.

        Pseries is great for large verticle apps, but for virtualization? No.
        • by tim620 (1052986)
          1. You get what you pay for. Yes, pSeries hardware costs a ton of $ (iSeries even more so). However, you get top notch hardware and an OS designed around the hardware. Much more stability, scalability and redundancy than any linux box than has been slapped together. 2. You evidently have never used any virtualization on a pSeries/AIX machine. AIX runs circles around VMware ESX, etc. Any resourse allocation can be changed on the fly without taking down any of the OS's involved in the reallocation. You
        • Sounds like normal 3-phase power. Standard in industrial units and farms.
    • With 1u pizzaboxen I can eazity go up to 24 kW in a rack. While our p595 can be cooled by 4 kW room / raised floor cooling. Not needing to do excessive cooling is greener.
  • I never understood the push for Linux on iSeries or pSeries. To me, if you want 'nix on pSeries just run AIX.
    • Re: (Score:2, Insightful)

      by cgh4be (182894)
      I think there are a couple of reasons:

      1) There are some (not many, but some) applications that run on Linux that don't run on AIX (i.e. won't compile on AIX)
      2) There are a lot of Linux gearheads out there that a company might not want to retrain for AIX

      The whole point is to be able to run (almost) any operating system you own on (almost) any platform IBM sells. If Windows and Intel weren't in bed, Windows would be running on the pSeries. In fact, it is in the lab, it's just not for sale :)
      • by no_pets (881013)
        FFIW we ran Windows on the iSeries. Of course it wasn't running on a POWER processor. The iSeries had what they called an IXS (Integrated xSeries Server) which was basically a daughter card with an Intel processor on it. I'm not sure if you can get one of those cards in a pSeries or not but the xSeries (or whatever they call them now) would be the way I would want to run Linux on IBM hardware.

        I'll buy what you said about IBM wanting customers to be able to run any OS on any of their hardware. I just thin
    • Yes, but if you know Linux on x86 already, it's that much simpler just to run Linux on POWER and retain most of your knowledge. This however is more like using WINE/VMware to run your Linux86 apps, but still use AIX, making it easier to migrate
    • Linux has mindshare, and by supporting Linux on lower-end systems, IBM sells businesses Power-based small systems (only available from them), and then gently moves them up the food chain as their needs increase. This way you have IBM 2-core OpenPower systems, and IBM p595s, and eventually (salesmen look off into the distance picturing the bahamas) a Z-series mainframe, all capable of being partitioned to still run the same apps. It's part of their policy of making sure they have a solution for any size of
  • This is the point. (Score:4, Informative)

    by HockeyPuck (141947) on Monday April 23, 2007 @05:42PM (#18846051)
    In the current generation of Power CPUs, you can implement micropartitions, akin to "this partition uses .1 CPUs", which if you've got spare computational power available on your AIX system, you could create additional partitions for X86 use. Also, since the partitions have the ability to communicate directly with each other without going over an external network, you could have in one chassis an AIX database with a linux based webserver in different partitions, both sharing the same fibrechannel cards and external gigE/10Gig network connections.
    • Or you could do the same thing with VMware ESX.
      • True, but IBM is providing those shops which already have IBM powerPC 'big iron' and opportunity to leverage it for non-ppc environments.
      • by hey! (33014)
        I suppose you should look at something like a rack full of blade servers plus SAN plus VMWare on one hand, and a high end IBM p series on the other.

        It seems to me that while the applications for each have some overlap, they're quite distinct. I'd go the VMWare direction if I wanted to virtualize a number of Windows servers or run a number of x86 applications for I only had binaries. I'd go with IBM if binary compatibility were not an issue, because it is simpler and has options the VMWare solution doesn't
    • BUZZ.

      You're speaking of Virtual I/O Server (VIOS). The point the marketing/sales folks like to forget is that those VIOS suck up CPU and add one (or two if redundancy is important [gee!]) more system to maintain.

      Oh, and VIOS is really just a customized AIX with a severely bastardized command set, meaning admins have to have a VIO hat to put on.

      VIOS offers some good features, but silver bullet it ain't.

      Micropartitioning is too new for most folks to get their head around.
      • by mink (266117)
        For what he describes, you do not need VIOS.

        As long as a partition has 1 disk and 1 net port of some type you dont need virtualized I/O. The limit on partitions is the number of PCI adapters you can put storage on (each lpar gets a pci slot for disk I/O of some type). You can also have physical nics only on the external facing partition and still give them virtual network adapters. Keep the backend stuff with only virtual nics (by not using VIO to bridge the virtual and physic nets you do lose the ability t
    • by mink (266117)
      Micro Partitioning is even better then that.
      You need a minimum of .1 cpu to start an lpar, but you can add to it in .01 increments (and take away in that same amount down to the original .1).
  • by Anonymous Coward
    Transitive has a news article ... it's them again, same tech provider as Apple uses for their Rosetta product (obviously, reverse of the technology, Intel -> PPC, instead of PPC -> Intel).

    http://transitive.com/news/news_20070423.htm [transitive.com]
  • More details (Score:5, Informative)

    by aktzin (882293) on Monday April 23, 2007 @06:18PM (#18846549)
    The article and press release don't say much, but I found this announcement on the IBM web site: http://www-03.ibm.com/systems/p/linux/systempave.h tml [ibm.com]

    At the bottom are some good details:

    "Runs most x86 Linux applications except those that * Directly access HW; * Are hardware architecture specific; * Provide unique kernel modules; or * Use instructions added later than the Pentium II processor, e.g. SSE2."

    "All application components and plug-ins must meet these qualifications. Support for x86 Linux applications requires an Red Hat 4 update 4 or Novell SLES 9 with Service Pack 3 of the Linux operating system."

    • The part about "Directly accessing HW" is what makes this not near as great for me as what I originally hoped. This will do nothing to make games run on Linux on Power. Let me know when that's a posibility, and then also when there is a nice Power desktop available again.
      • Re: (Score:3, Informative)

        by Lorkki (863577)
        This likely isn't something that would just work on your PowerPC desktop anyway. The POWER architecture is aimed at a completely different market, for bigger servers and the like, and the instruction set is a superset of PPC's. Moreover, games these days use various HAL APIs to talk with acceleration hardware rather than directly accessing it - you'd want something like WINE with an x86 emulator, but DOSBox is available for PPC platforms if you need to run those older titles.
  • Why, we could even load them with Ubuntu ...
    • Re: (Score:3, Funny)

      And then what, set them up in a Beowulf cluster?

      Never would have thought of it before.
      • Re: (Score:2, Funny)

        by WillAffleckUW (858324)
        Why yes, a virtual Beowulf cluster!

        But, first, we could argue over whether they would work better with BSD or Linux ...
  • by PaulBu (473180) on Monday April 23, 2007 @06:32PM (#18846731) Homepage
    As far as I remember one of the original goals of PPC architecture in the times of original IBM/Moto/Apple consortium 15 years ago was to be able to emulate "other" (x86, maybe? ;-) ) processors efficiently. Strangely I have not heard about something like this being actually used up until today! (Yes, I know that POWER != PPC, but I think the parts are still there).

    Paul B.
    • Re: (Score:1, Informative)

      by Anonymous Coward
      PowerPC is not designed to emulate other arch.

      Good point of designed (compared to x86),
      1) It is a 64-bit architecture with 2 adressing mode 32-bit and 64-bit. Some implementations (ex: from Motorola in Mac) were implementing only the 32-bit portion. But the arch itself has been designed 64-bit from the start.

      2) Virtualization. There are issues with the x86 that makes it difficult to virtualize. The PowerPC does not have these issues.

      POWER. There is the old POWER architecture.

      But when we talk about IBM
      • by PaulBu (473180)
        It's a pity you posted as AC -- thus, most likely will not see this :) -- but thanks for refreshing my memory!

        Yes, it was a bit confusing, first I had to find out that POWER!=PowerPC, pretty soon after that that there is almost a seamless transition between the two... I guess I stopped following that story between POWER3 and POWER4, which left me in a bit confused state! :)

        But I still stand by me recollection that one of the original goals was to make all x86 programs (including Windows of that time) effic
        • I still stand by me recollection that one of the original goals was to make all x86 programs (including Windows of that time) efficiently runnable

          AIX 3.1 came with a 286 simulator. It was not terribly fast, especially for graphics, but it was there. Note that this was simulating a segmented architecture, not too easy to do. Compared to some other architectures at that time, POWER was reasonlably good at bit extraction/insertion, which helps when you are trying to emulate another architecture. There was also

    • by salimma (115327)
      A bit bizarre that IBM does this after they decided to make POWER exclusively big-endian (starting from POWER4 / PPC 970, if I remember correctly). Before that it's endian-neutral, so writing an emulation layer is easier because you don't have to deal with endianness issues.

      One of the reason for the relative performance drop of Virtual PC when run on a G5 rather than a G4 Mac is the software handling of endianness. (And yes, emulation of Intel x86 CPU on PPC has been done for a long time. Just not on the se
      • A bit bizarre that IBM does this after they decided to make POWER exclusively big-endian

        The PPC 970 doesn't have the "optional little-endian facility," but the 970 is not used in the high-end boxes. I'm not aware of any high-end Power implementation without little-endian support. In particular, IBM says that POWER5 has it.


        Why the 970 doesn't have it beats me. Perhaps someone muffed the implementation or thought they could save a few cents per processor.

        • by salimma (115327)
          Ah, my mistake. Hmm, perhaps IBM knew they would have problems ramping up the clock speed on the 970, and so tried to throw out as many unneeded circuitry as possible?

          It's their first CPU with AltiVec/VMX support, after all. And if Apple users were pissed off at the slower emulation of x86 code, imagine how murderous they'd get if AltiVec were left out!
    • by Blakey Rat (99501)
      Apple used PPC chips to emulate Motorola 68k CPUs for ages. They only recently stopped supporting that configuration, with the switch to Intel. (Now Apple has their Intel Core CPUs emulating the PPC CPUs.)

      The coolest part is that when Apple does an architecture switch like this, their emulation is so fast and bug-free (not 100%, but good) that you couldn't even tell the difference between running a 68k program or a PPC program most of the time.
  • Xbox 360 is PowerPC, right? Is that similar enough to get any benefit from this?
  • Wonder how this compares to em86? I recall mention of that a few years back as a way to run x86 linux apps on alpha cpus. Not sure DEC/Compaq/HP ever released the source to the x86 execution engine, but em86 was pretty cool back in the day nonetheless..
  • Regardless of how practical this is, it's an awesome checkbox feature for corporate weenies advocating the POWER architecture superminis with no clue about their true strengths.

    "Look, this machine is so powerful it can run qemu user-mode emulation of another processor in its spare time! Let's see your Dell cluster emulate an x86!"
  • AVE' IT!
  • This is not an IBM technology, but instead is based on a technology developed by Transitive.

    It would be much more useful if IBM would offer the version of Transitive software which allows POWER applications to run on x86 systems, rather than the reverse. The only thing which makes sense to run on a emulator on a IBM POWER system would be a mainframe environment.

    Why emulate the most mass-produced CPU instruction set ever, given the ISA is still in mass production? Why emulate the cheap volume processor on

IF I HAD A MINE SHAFT, I don't think I would just abandon it. There's got to be a better way. -- Jack Handley, The New Mexican, 1988.

Working...